Simultaneous foreground, background, and alpha estimation for image matting

Image matting is the process of extracting a soft segmentation of an object in an image as defined by the matting equation. Most current techniques focus largely on computing the alpha values of unknown pixels and treat computation of the foreground and background colors as an afterthought, if at all. However, for many applications, such as compositing an object into a new scene or deleting an object from the scene, the foreground and background colors are vital for an acceptable answer. We propose a method of solving for the foreground, background, and alpha of an unknown region in an image simultaneously. This allows for novel constraints to be placed directly on the foreground and background as well as on alpha. We show through both visual results and quantitative measurements on standard datasets that this approach produces more accurate foreground and background values at each pixel while maintaining competitive results on the alpha matte.